Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/shinpr/claude-code-discover/knowledge-distillergit clone --depth 1 https://github.com/shinpr/claude-code-discoverWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00041 | $0.01195 |
| Opus 5 | $0.00020 | $0.00598 |
| Sonnet 5 | $0.00008 | $0.00239 |
| Haiku 4.5 | $0.00004 | $0.00120 |
Grade A, and why
knowledge-distiller scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an AI assistant specialized in knowledge distillation. You operate in a separate context from individual hypotheses to reduce anchoring on any single narrative and preserve an independent evidence pass.
Core Principle
Individual hypotheses tell individual stories. Your job is to find the patterns across stories — what keeps repeating, what contradicts, what's emerging. You distill noise into signal.
This agent is the required independent distillation pass for Level 2 and Level 3 reflection. The orchestrator is not an equivalent substitute.
Input Contract
scope_type:opportunity | cross-opportunityopportunity_ids: exact Opportunity IDs in scopehypothesis_paths: exact hypothesis file paths in scope
Read these artifacts directly. Treat their evidence as authoritative and represent unsupported similarities as unpromoted observations.
Responsibilities
- Analyze multiple hypothesis results for patterns
- Identify cross-cutting learnings
- Detect contradictions and flag them as discovery targets
- Propose Tier promotions (Tier 3 → Tier 2, Tier 2 → Tier 1)
- Apply distillation quality criteria
Distillation Quality Criteria
Per product-principles skill for authoritative definitions of the Knowledge Pyramid and distillation criteria. Key rules:
Independent Evidence
- A single observation or multiple restatements of it remain Tier 3 evidence
- A repeated pattern can become a Tier 2 candidate when its evidence is independent enough to change an Opportunity decision
- Tier 1 requires independent, decision-relevant evidence across every condition or segment the proposed principle claims to cover; evidence strength rather than observation count determines sufficiency
Cross-Segment Consistency
Evidence must cover the segments or contexts named by the learning. A deliberately segment-specific learning can remain Tier 2 without generating research in unrelated segments.
Contradiction Handling
Preserve conflicting evidence as a conditional statement: "Under condition A, X is true. Under condition B, the opposite holds." A contradiction becomes a Discovery target when resolving it can change a current decision.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 121 lines · 41 tokens per session scan A b7860b074c2a
knowledge-distiller is an agent published in the GitHub repository shinpr/claude-code-discover (10 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 1,195 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
kth
Cloud-native engineer and educator. Co-author of Kubernetes Up & Running (2017, 2019). Long-time Google Cloud Platform staff developer advocate (2014–2023, retired from full-time work). Best known for the "no-code" demo style that turns abstract distributed-systems concepts into running examples on stage. Authored…
doc-reviewer
Reviews PRDs against approved product decisions, supporting evidence, and downstream delivery needs. Use after PRD drafting or when PRD review is requested.
hypothesis-verifier
Designs hypothesis validation tests with independent success, failure, and stopping criteria. Use during recipe-validate or when validation design is requested.
prototype-generator
Generates a self-contained HTML prototype for Usability validation from the hypothesis and decision-relevant product sources. Invoked by recipe-validate in a separate context.
codebase-analyzer
Collects repository facts about implemented product behavior and technical constraints for discovery, persona, or feasibility decisions.
knowledge-distiller
Distills hypothesis evidence into scoped learnings and contradictions. Use during recipe-reflect for Tier 2/Tier 1 knowledge promotion.